In [22]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px

data = pd.read_csv("C:/Users/priya/Documents/GitHub/OIBSIP/Task-2_unemployment/Unemployment in India.csv")
print(data.head())
           States         Date  Frequency   EUR        EE   ELPR   Area Region
0  Andhra Pradesh   31-05-2019    Monthly  3.65  11999139  43.24  Rural  South
1  Andhra Pradesh   30-06-2019    Monthly  3.05  11755881  42.05  Rural  South
2  Andhra Pradesh   31-07-2019    Monthly  3.75  12086707  43.50  Rural  South
3  Andhra Pradesh   31-08-2019    Monthly  3.32  12285693  43.97  Rural  South
4  Andhra Pradesh   30-09-2019    Monthly  5.17  12256762  44.68  Rural  South
In [23]:
print(data.isnull().sum())
States        0
 Date         0
 Frequency    0
 EUR          0
EE            0
ELPR          0
Area          0
Region        0
dtype: int64
In [24]:
data.columns= ["States","Date","Frequency","EUR","EE","ELPR","Area","Region"]
In [25]:
plt.style.use('seaborn-whitegrid')
plt.figure(figsize=(12, 10))
sns.heatmap(data.corr())
plt.show()
In [26]:
# Set the column names for your data
data.columns = ["States", "Date", "Frequency", "EUR", "EE", "ELPR", "Area","Region"]

# Set the figure size and create a new subplot
fig, ax = plt.subplots(figsize=(15, 12))

# Set the title of the plot
plt.title("Indian Unemployment")

# Create the histogram plot using Seaborn
sns.histplot(x="EE", hue="States", data=data, ax=ax)

# Display the plot
plt.show()
In [27]:
plt.figure(figsize=(12, 10))
plt.title("Indian Unemployment")
sns.histplot(x="EUR", hue="States", data=data)
plt.show()
In [28]:
unemploment = data[["States", "Region", "EUR"]]
figure = px.sunburst(unemploment, path=["States","Region"], 
                     values="EUR", 
                     width=700, height=700, color_continuous_scale="RdYlGn", 
                     title="Unemployment Rate in India")
figure.show()